The best StepFun model for RAG is Step 3.7 Flash — 30.3 intelligence with 262K tokens of context for retrieved passages. Step 3.5 Flash (26.0) is next.
The best AI models for retrieval-augmented generation, ranked by intelligence among models with at least 128K tokens of context — enough to hold retrieved passages plus conversation. RAG pipelines run at volume, so weigh the price and speed columns as hard as the score.
The best StepFun model for RAG is Step 3.7 Flash — 30.3 intelligence with 262K tokens of context for retrieved passages. Step 3.5 Flash (26.0) is next.
Step 3.5 Flash (26.0) is the closest alternative on this metric. See the full ranking above for the tradeoffs.
modelgrep tracks 2 StepFun models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Step 3.7 Flash. 2 of them qualify for this ranking.